/**
* rdma_rw_mr_factor - return number of MRs required for a payload
* @device: device handling the connection
* @port_num: port num to which the connection is bound
* @maxpages: maximum payload pages per rdma_rw_ctx
*
* Returns the number of MRs the device requires to move @maxpayload
* bytes. The returned value is used during transport creation to
* compute max_rdma_ctxts and the size of the transport's Send and
* Send Completion Queues.
*/
unsigned int rdma_rw_mr_factor(struct ib_device *device, u8 port_num,
unsigned int maxpages)
{
unsigned int mr_pages;
if (rdma_rw_can_use_mr(device, port_num))
mr_pages = rdma_rw_fr_page_list_len(device);
else
mr_pages = device->attrs.max_sge_rd;
return DIV_ROUND_UP(maxpages, mr_pages);
}
int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr)
{
struct ib_device *dev = qp->pd->device;
u32 nr_mrs = 0, nr_sig_mrs = 0;
int ret = 0;
if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN) {
nr_sig_mrs = attr->cap.max_rdma_ctxs;
nr_mrs = attr->cap.max_rdma_ctxs * 2;
} else if (rdma_rw_can_use_mr(dev, attr->port_num)) {
nr_mrs = attr->cap.max_rdma_ctxs;
}
if (nr_mrs) {
ret = ib_mr_pool_init(qp, &qp->rdma_mrs, nr_mrs,
IB_MR_TYPE_MEM_REG,
rdma_rw_fr_page_list_len(dev));
if (ret) {
pr_err("%s: failed to allocated %d MRs\n",
__func__, nr_mrs);
return ret;
}
}
if (nr_sig_mrs) {
ret = ib_mr_pool_init(qp, &qp->sig_mrs, nr_sig_mrs,
IB_MR_TYPE_SIGNATURE, 2);
if (ret) {
pr_err("%s: failed to allocated %d SIG MRs\n",
__func__, nr_mrs);
goto out_free_rdma_mrs;
}
}
return 0;
out_free_rdma_mrs:
ib_mr_pool_destroy(qp, &qp->rdma_mrs);
return ret;
}
static int rdma_rw_init_one_mr(struct ib_qp *qp, u8 port_num,
struct rdma_rw_reg_ctx *reg, struct scatterlist *sg,
u32 sg_cnt, u32 offset)
{
u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device);
u32 nents = min(sg_cnt, pages_per_mr);
int count = 0, ret;
reg->mr = ib_mr_pool_get(qp, &qp->rdma_mrs);
if (!reg->mr)
return -EAGAIN;
if (reg->mr->need_inval) {
reg->inv_wr.opcode = IB_WR_LOCAL_INV;
reg->inv_wr.ex.invalidate_rkey = reg->mr->lkey;
reg->inv_wr.next = ®->reg_wr.wr;
count++;
} else {
reg->inv_wr.next = NULL;
}
ret = ib_map_mr_sg(reg->mr, sg, nents, &offset, PAGE_SIZE);
if (ret < nents) {
ib_mr_pool_put(qp, &qp->rdma_mrs, reg->mr);
return -EINVAL;
}
reg->reg_wr.wr.opcode = IB_WR_REG_MR;
reg->reg_wr.mr = reg->mr;
reg->reg_wr.access = IB_ACCESS_LOCAL_WRITE;
if (rdma_protocol_iwarp(qp->device, port_num))
reg->reg_wr.access |= IB_ACCESS_REMOTE_WRITE;
count++;
reg->sge.addr = reg->mr->iova;
reg->sge.length = reg->mr->length;
return count;
}
/**
* rdma_rw_ctx_signature init - initialize a RW context with signature offload
* @ctx: context to initialize
* @qp: queue pair to operate on
* @port_num: port num to which the connection is bound
* @sg: scatterlist to READ/WRITE from/to
* @sg_cnt: number of entries in @sg
* @prot_sg: scatterlist to READ/WRITE protection information from/to
* @prot_sg_cnt: number of entries in @prot_sg
* @sig_attrs: signature offloading algorithms
* @remote_addr:remote address to read/write (relative to @rkey)
* @rkey: remote key to operate on
* @dir: %DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
*
* Returns the number of WQEs that will be needed on the workqueue if
* successful, or a negative error code.
*/
int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
u8 port_num, struct scatterlist *sg, u32 sg_cnt,
struct scatterlist *prot_sg, u32 prot_sg_cnt,
struct ib_sig_attrs *sig_attrs,
u64 remote_addr, u32 rkey, enum dma_data_direction dir)
{
struct ib_device *dev = qp->pd->device;
u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device);
struct ib_rdma_wr *rdma_wr;
struct ib_send_wr *prev_wr = NULL;
int count = 0, ret;
if (sg_cnt > pages_per_mr || prot_sg_cnt > pages_per_mr) {
pr_err("SG count too large\n");
return -EINVAL;
}
ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);
if (!ret)
return -ENOMEM;
sg_cnt = ret;
ret = ib_dma_map_sg(dev, prot_sg, prot_sg_cnt, dir);
if (!ret) {
ret = -ENOMEM;
goto out_unmap_sg;
}
prot_sg_cnt = ret;
ctx->type = RDMA_RW_SIG_MR;
ctx->nr_ops = 1;
ctx->sig = kcalloc(1, sizeof(*ctx->sig), GFP_KERNEL);
if (!ctx->sig) {
ret = -ENOMEM;
goto out_unmap_prot_sg;
}
ret = rdma_rw_init_one_mr(qp, port_num, &ctx->sig->data, sg, sg_cnt, 0);
if (ret < 0)
goto out_free_ctx;
count += ret;
prev_wr = &ctx->sig->data.reg_wr.wr;
if (prot_sg_cnt) {
ret = rdma_rw_init_one_mr(qp, port_num, &ctx->sig->prot,
prot_sg, prot_sg_cnt, 0);
if (ret < 0)
goto out_destroy_data_mr;
count += ret;
if (ctx->sig->prot.inv_wr.next)
prev_wr->next = &ctx->sig->prot.inv_wr;
else
prev_wr->next = &ctx->sig->prot.reg_wr.wr;
prev_wr = &ctx->sig->prot.reg_wr.wr;
} else {
ctx->sig->prot.mr = NULL;
}
ctx->sig->sig_mr = ib_mr_pool_get(qp, &qp->sig_mrs);
if (!ctx->sig->sig_mr) {
ret = -EAGAIN;
goto out_destroy_prot_mr;
}
if (ctx->sig->sig_mr->need_inval) {
memset(&ctx->sig->sig_inv_wr, 0, sizeof(ctx->sig->sig_inv_wr));
ctx->sig->sig_inv_wr.opcode = IB_WR_LOCAL_INV;
ctx->sig->sig_inv_wr.ex.invalidate_rkey = ctx->sig->sig_mr->rkey;
prev_wr->next = &ctx->sig->sig_inv_wr;
prev_wr = &ctx->sig->sig_inv_wr;
}
ctx->sig->sig_wr.wr.opcode = IB_WR_REG_SIG_MR;
ctx->sig->sig_wr.wr.wr_cqe = NULL;
ctx->sig->sig_wr.wr.sg_list = &ctx->sig->data.sge;
ctx->sig->sig_wr.wr.num_sge = 1;
ctx->sig->sig_wr.access_flags = IB_ACCESS_LOCAL_WRITE;
ctx->sig->sig_wr.sig_attrs = sig_attrs;
ctx->sig->sig_wr.sig_mr = ctx->sig->sig_mr;
if (prot_sg_cnt)
ctx->sig->sig_wr.prot = &ctx->sig->prot.sge;
prev_wr->next = &ctx->sig->sig_wr.wr;
prev_wr = &ctx->sig->sig_wr.wr;
count++;
ctx->sig->sig_sge.addr = 0;
ctx->sig->sig_sge.length = ctx->sig->data.sge.length;
if (sig_attrs->wire.sig_type != IB_SIG_TYPE_NONE)
ctx->sig->sig_sge.length += ctx->sig->prot.sge.length;
rdma_wr = &ctx->sig->data.wr;
rdma_wr->wr.sg_list = &ctx->sig->sig_sge;
rdma_wr->wr.num_sge = 1;
rdma_wr->remote_addr = remote_addr;
rdma_wr->rkey = rkey;
if (dir == DMA_TO_DEVICE)
rdma_wr->wr.opcode = IB_WR_RDMA_WRITE;
else
rdma_wr->wr.opcode = IB_WR_RDMA_READ;
prev_wr->next = &rdma_wr->wr;
prev_wr = &rdma_wr->wr;
count++;
return count;
out_destroy_prot_mr:
if (prot_sg_cnt)
ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->sig->prot.mr);
out_destroy_data_mr:
ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->sig->data.mr);
out_free_ctx:
kfree(ctx->sig);
out_unmap_prot_sg:
ib_dma_unmap_sg(dev, prot_sg, prot_sg_cnt, dir);
out_unmap_sg:
ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
return ret;
}
static int rdma_rw_init_mr_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
u8 port_num, struct scatterlist *sg, u32 sg_cnt, u32 offset,
u64 remote_addr, u32 rkey, enum dma_data_direction dir)
{
u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device);
int i, j, ret = 0, count = 0;
ctx->nr_ops = (sg_cnt + pages_per_mr - 1) / pages_per_mr;
ctx->reg = kcalloc(ctx->nr_ops, sizeof(*ctx->reg), GFP_KERNEL);
if (!ctx->reg) {
ret = -ENOMEM;
goto out;
}
for (i = 0; i < ctx->nr_ops; i++) {
struct rdma_rw_reg_ctx *prev = i ? &ctx->reg[i - 1] : NULL;
struct rdma_rw_reg_ctx *reg = &ctx->reg[i];
u32 nents = min(sg_cnt, pages_per_mr);
ret = rdma_rw_init_one_mr(qp, port_num, reg, sg, sg_cnt,
offset);
if (ret < 0)
goto out_free;
count += ret;
if (prev) {
if (reg->mr->need_inval)
prev->wr.wr.next = ®->inv_wr;
else
prev->wr.wr.next = ®->reg_wr.wr;
}
reg->reg_wr.wr.next = ®->wr.wr;
reg->wr.wr.sg_list = ®->sge;
reg->wr.wr.num_sge = 1;
reg->wr.remote_addr = remote_addr;
reg->wr.rkey = rkey;
if (dir == DMA_TO_DEVICE) {
reg->wr.wr.opcode = IB_WR_RDMA_WRITE;
} else if (!rdma_cap_read_inv(qp->device, port_num)) {
reg->wr.wr.opcode = IB_WR_RDMA_READ;
} else {
reg->wr.wr.opcode = IB_WR_RDMA_READ_WITH_INV;
reg->wr.wr.ex.invalidate_rkey = reg->mr->lkey;
}
count++;
remote_addr += reg->sge.length;
sg_cnt -= nents;
for (j = 0; j < nents; j++)
sg = sg_next(sg);
offset = 0;
}
ctx->type = RDMA_RW_MR;
return count;
out_free:
while (--i >= 0)
ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->reg[i].mr);
kfree(ctx->reg);
out:
return ret;
}
